爬取房价信息_python爬虫_

import requests import bs4 import openpyxl year = input("请输入要查询的年份：") def get(): url = "https://www.58.com/fangjiawang/quanguo-%s/"%year UserAgent = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36" Referer = "https://www.58.com/fangjiawang/quanguo-%s/"%url[-5:-1] headers={"User-Agent":UserAgent,"Referer":Referer} response = requests.get(url,headers) return response def targets(): response = get() content = bs4.BeautifulSoup(response.text,"html.parser") targetall = content.find_all("ul",class_="box-price") #这里注意find_all返回一个数据集列表，而数据集合列表无属性，需要单独拿出来 return targetall ''' target = targetall[0].find_all("a") print("2020年全国房价排行榜") for target in target: print(target.b.text,end="\t") print(target.span.text,end="\t") print(target.em.text,end="\n") target = targetall[1].find_all("a") print("2020年全国房价涨幅榜") for target in target: print(target.b.text,end="\t") print(target.span.text,end="\t") print(target.em.text,end="\n") target = targetall[2].find_all("a") for target in target: print("2020年全国房价跌幅榜") print(target.b.text,end="\t") print(target.span.text,end="\t") print(target.em.text,end="\n") ''' def ToExcel(): targetall = targets() wb = openpyxl.Workbook()#新建工作簿 ws = wb.create_sheet(index=0,title = "%s年全国房价排行榜"%year)#在索引值为0处加入一个新工作表 count=1 ws["a1"] = "地区" ws["b1"] = "房价" ws["c1"] = "涨幅率" target = targetall[0].find_all("a") for target in target: count +=1 ws["a%s"%count] = target.b.text ws["b%s"%count] = target.span.text ws["c%s"%count] = target.em.text ws = wb.create_sheet(index=1,title = "%s年全国房价涨幅榜"%year) count=1 ws["a1"] = "地区" ws["b1"] = "房价" ws["c1"] = "涨幅率" target = targetall[1].find_all("a") for target in target: count +=1 ws["a%s"%count] = target.b.text ws["b%s"%count] = target.span.text ws["c%s"%count] = target.em.text ws = wb.create_sheet(index=2,title = "%s年全国房价跌幅榜"%year) count=1 ws["a1"] = "地区" ws["b1"] = "房价" ws["c1"] = "涨幅率" target = targetall[2].find_all("a") for target in target: count +=1 ws["a%s"%count] = target.b.text ws["b%s"%count] = target.span.text ws["c%s"%count] = target.em.text string = "%s年全国房价信息.xlsx"%year wb.save(string)#保存为excel if __name__ == "__main__": ToExcel()